Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1246 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.8504. Min Act: -0.1700

Data Index: 8332756 (Open Web Text)

Max Activating Token Index: 256

Text #1

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.8361. Min Act: -0.1700

Data Index: 8348619 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.8352. Min Act: -0.1700

Data Index: 5693004 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.8306. Min Act: -0.1700

Data Index: 5766065 (Open Web Text)

Max Activating Token Index: 209

Text #4

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.8001. Min Act: -0.1700

Data Index: 2524748 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7450. Min Act: -0.1700

Data Index: 2824236 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7790. Min Act: -0.1700

Data Index: 3724289 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1580936 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7471. Min Act: -0.1700

Data Index: 1732823 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7011. Min Act: -0.1700

Data Index: 2087227 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6998. Min Act: -0.1700

Data Index: 2507546 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7077. Min Act: -0.1700

Data Index: 8193225 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7083. Min Act: -0.1700

Data Index: 5962788 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.7416. Min Act: -0.1700

Data Index: 5958177 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6668. Min Act: -0.1700

Data Index: 2098335 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6718. Min Act: -0.1700

Data Index: 2862682 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6715. Min Act: -0.1700

Data Index: 6864312 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6792. Min Act: -0.1700

Data Index: 4225929 (Open Web Text)

Max Activating Token Index: 549

Text #18

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6668. Min Act: -0.1700

Data Index: 7729528 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.8504. Min Range: -3.8504

Max Act: 3.6479. Min Act: -0.1700

Data Index: 5646644 (Open Web Text)

Max Activating Token Index: 291